AAAI 2026 Papers

More and more organizations are relying on Machine Learning (ML) models to support internal decision-making processes. To better support such processes, it would be highly beneficial to contextualize the inductively acquired knowledge encoded in these models and enable formal reasoning over it. Despite significant progress in Neural-Symbolic AI, this specific challenge remains largely under-explored. We propose a framework that allows to integrate the knowledge induced by ML classifiers with the knowledge specified by logic-based formalisms. The framework is based on the novel notion of Hybrid Knowledge Base (HKB), consisting of two components: an ontology and a set of ML binary classifiers. As usual, the ontology provides an intensional representation of the modeled domain through logic-based axioms, while the binary classifiers implicitly encode the extensional knowledge. Specifically, a HKB associates to each concept and role mentioned in the ontology a classifier based on a set of features deemed to be relevant for the application domain, thereby virtually populating the concepts and roles with the instances and pairs of instances from the feature space. Besides the definition of the new framework, as a more technical contribution we show how to reason in this framework by studying query answering over HKBs. In particular, we investigate the computational complexity of query answering in a rich language over HKBs in which the ontology is specified in (the Description Logic counterpart of) RDFS, while the binary classifiers are represented by Multi-Layer Perceptrons.

Spatial representation learning is fundamental to GeoAI applications, including urban analytics, as it encodes the shapes, locations, and spatial relationships (topological and distance-based) of geo-entities such as points, polylines, and polygons. Existing methods either target a single geo-entity type or, like Poly2Vec, decompose entities into simpler components to enable Fourier transformation, introducing high computational cost. Moreover, since the transformed space lacks geometric alignment, these methods rely on uniform, non-adaptive sampling, which blurs fine-grained features like edges and boundaries. To address these limitations, we introduce Geo2Vec, a novel method inspired by signed distance fields (SDF) that operates directly in the original space. Geo2Vec adaptively samples points and encodes their signed distances (positive outside, negative inside), capturing geometry without decomposition. A neural network trained to approximate the SDF produces compact, geometry-aware, and unified representations for all geo-entity types. Additionally, we propose a rotation-invariant positional encoding to model high-frequency spatial variations and construct a structured and robust embedding space for downstream GeoAI models. Empirical results show that Geo2Vec consistently outperforms existing methods in representing shape and location, capturing topological and distance relationships, and achieving greater efficiency in real-world GeoAI applications.

Competency Questions (CQs) play a crucial role in validating ontology design. While manually crafting CQs can be highly time-consuming and costly for ontology engineers, recent studies have explored the use of large language models (LLMs) to automate this process. However, prior approaches have largely evaluated generated CQs based on their similarity to existing datasets, which often fail to verify semantic pitfalls such as “Misusing allValuesFrom”. Since such pitfalls cannot be reliably detected through rule-based methods, we propose a novel dataset and model of Validating Semantic Pitfalls in Ontology (VSPO) for CQ generation specifically designed to verify the semantic pitfalls. To simulate missing and misused axioms, we use LLM to generate natural language definitions of classes and properties and introduce misalignments between the definitions and the ontology by removing axioms or altering logical operators (e.g., substituting union with intersection). We then fine-tune LLaMA-3.1-8B-Instruct to generate CQs that validate these semantic discrepancies between the provided definitions and the corresponding axioms. The resulting CQs can detect a broader range of modeling errors compared to existing public datasets. Our fine-tuned model demonstrates superior performance over baselines, showing 26% higher precision and 28.2% higher recall than GPT-4.1 in generating CQs for pitfall validation. This research enables automatic generation of TBox-validating CQs using LLMs, significantly reducing manual effort while improving semantic alignment between ontologies and expert knowledge. To the best of our knowledge, this is the first study to target semantic pitfall validation in CQ generation using LLMs.

In runtime verification, monitoring consists of analyzing the current execution of a system and determining, on the basis of the observed finite trace, whether all its possible continuations satisfy or violate a given specification. This is typically done by synthesizing a monitor–often a Deterministic Finite State Automaton (DFA)–from logical specifications expressed in Linear Temporal Logic (LTL) or in its finite-word variant (LTLf). Unfortunately, the size of the resulting DFA may incur a doubly exponential blow-up in the size of the formula. In this paper, we identify some conditions under which monitoring can be done without constructing such a DFA. We build on the notion of intentionally safe and cosafe formulas to show that monitoring of these formulas can be carried out through trace-checking, that is, by directly evaluating them on the current system trace, with a polynomial complexity in the size of both the trace and the formula. In addition, we investigate the complexity of recognizing intentionally safe and cosafe formulas for the safety and cosafety fragments of LTL and LTLf. As for LTLf, we show that all formulas in these fragments are intentionally safe and cosafe, thus removing the need for the check. As for LTL, we prove that the problem is in PSPACE, significantly improving over the EXPSPACE complexity of full LTL.

Deep Learning techniques are nowadays pervasive in AI. However, these approaches suffer from a lack of transparency for justifying their output and for helping users in believing in their decisions. For these reasons alternative approaches to learning deserve to be explored either for developing new tools with autonomous learning capability or for explaining the results of black-box predictors. Among them an important role is assumed since the Nineties by Inductive Logic Programming and, in particular, recently by the approaches of Learning from Answer Sets (LAS). Computing inductive solutions for LAS tasks is known to be Sigma P2 hard. In this work, we tackle this problem using a single-shot disjunctive ASP encoding based on the saturation technique originally proposed by Eiter and Gottlob. We prove that, when the background knowledge and hypothesis space form a tight program (a syntactical property) our encoding is linear in the size of the task. This approach contrasts with the state-of-the-art ILASP system, which relies on multiple iterative calls to an ASP solver. As a result, it can be directly evaluated by modern disjunctive ASP solvers, leveraging decades of research and optimization in the ASP community. We implement our method in a system named LASCO. Experimental results on a diverse set of benchmarks demonstrate that LASCO outperforms all versions of ILASP on many instances and it scales if run on multi-threaded machines.

In this paper, we study the data complexity of querying inconsistent weighted description logic (DL) knowledge bases under recently-introduced cost-based semantics. In a nutshell, the idea is to assign each interpretation a cost based upon the weights of the violated axioms and assertions, and certain and possible query answers are determined by considering all (resp. some) interpretations having optimal or bounded cost. Whereas the initial study of cost-based semantics focused on DLs between EL_bot and ALCO, we consider DLs that may contain inverse roles and role inclusions, thus covering prominent DL-Lite dialects. Our data complexity analysis goes significantly beyond existing results by sharpening several lower bounds and pinpointing the precise complexity of optimal-cost certain answer semantics (no non-trivial upper bound was known). Moreover, while all existing results show the intractability of cost-based semantics, our most challenging and surprising result establishes that if we consider DL-Lite^H_bool ontologies and a fixed cost bound, certain answers for instance queries and possible answers for conjunctive queries can be computed using first-order rewriting and thus enjoy the lowest possible data complexity (AC0).

As the use of AI in society grows, addressing emerging biases is essential to prevent systematic discrimination. Several bias detection methods have been proposed, but, with few exceptions, these tend to ignore transparency. Instead, interpretability and explainability are core requirements for algorithmic fairness, even more so than for other algorithmic solutions, given the human-oriented nature of fairness. We present ABIDE (Argumentative BIas detection by DEbate), a novel framework that structures bias detection transparently as debate, guided by an underlying argument graph as understood in (formal and computational) argumentation. The arguments are about the success chances of groups in local neighbourhoods and the significance of these neighbourhoods. We evaluate ABIDE experimentally and demonstrate its strengths in performance against an argumentative baseline.

Computational argumentation studies fundamental methods for reasoning within Artificial Intelligence (AI). Two prominent subfields in computational argumentation are abstract argumentation and structured argumentation. Abstract argumentation focuses on the interactions between arguments, ignoring their internal structure, while structured approaches utilize a given knowledge base to construct the arguments. Thus, the latter approach incorporates the internal structure of arguments into the reasoning process. In this work we introduce a form of abstraction on the well established structured approach of Assumption-Based Argumentation (ABA). Our goal is to provide methods to simplify complicated scenarios, by applying clustering over defeasible parts. Abstraction, particularly clustering, has been explored in recent research on abstract argumentation and in the adjacent field of logic programming. In fact, while clustering has also been applied to ABA, our approach takes a different, or rather dual, direction. In contrast to prior work on over-approximation on ABA, we propose the dual approach of under-approximation. We provide semantics for reasoning over clustered frameworks in a sound manner relative to original semantics, ensuring that any set deemed acceptable in the clustered scenario corresponds to an acceptable set. We show properties of the under-approximating semantics and illustrate our approach using a conceptual example based on medical recommendations.

A fundamental use of knowledge bases (KBs) is query answering, i.e., retrieving the information entailed by the KB in response to a user query. When both the KB and the query are specified as logical formulae, the standard form of answer provided to users is the set of all certain answers (CAs): tuples of constants that satisfy the formula defining the query in every model of the logical theory defining the KB. Despite their wide adoption, CAs are known to be just a lossy representation of the information that a KB and a query provide. While several alternative answer languages have been proposed in the literature, no general consensus has emerged on the most suitable approach to query answering over ontological KBs, as each language comes with its own limitations. To address some of these issues, we introduce Regularly Recurrent Answers (RRAs), a novel answer language for queries over ontological KBs based on regular expressions. RRAs support the representation of infinite sets of tuples of constants via a simple (and arguably well understood) generation mechanism. We show that RRAs can capture a fundamental fragment of the certain information entailed by union of conjunctive queries and DL-Lite KBs, making them a strong candidate for informative query answering settings. Our contribution includes the formal definition of RRAs, a proof of their informativeness, and a study of the computational complexity of query answering problem using RRAs.

Assessing the strength of arguments is essential for determining the outcomes of any argument-based system. A wide range of semantics has been proposed in the literature. These take as input a set of arguments—each assigned a basic weight and potentially subject to attacks from others—and compute a single strength value for each argument. Despite the diversity of argument types (or schemes), existing semantics apply uniform evaluation criteria across all arguments. In this paper, we advocate for type-dependent evaluations, acknowledging that the impact of attacks can vary across types. Given that many argument-based systems involve heterogeneous types of arguments, we propose a broad family of hybrid semantics that combine distinct base semantics, each tailored to specific argument types. We investigate their theoretical properties, present concrete instances within this family, and examine their computational complexity.

Recently, there has been an increasing interest in extending Dung's framework with probability theory, leading to the Probabilistic Argumentation Framework (PAF), and with supports in addition to attacks, leading to the Bipolar Argumentation Framework (BAF). In this paper, we introduce the Conditional Probabilistic Bipolar Argumentation Framework (CPBAF), which extends Probabilistic and Bipolar AF by allowing conditional probabilities on arguments, attacks, and on (possibly cyclic) supports. In this setting, we address the problem of computing the probability that a given argument is accepted. This is carried out by introducing the concept of probabilistic explanation for a given (probabilistic) extension. We show that the complexity of the problem is FP^#P-hard and propose polynomial approximation algorithms with bounded additive error for CPBAF where cycles with an odd number of attacks are forbidden.

We present NoReGeo, a novel benchmark designed to evaluate the intrinsic geometric understanding of large language models (LLMs) without relying on reasoning or algebraic computation. Unlike existing benchmarks that primarily assess models' proficiency in reasoning-based geometry-where solutions are derived using algebraic methods-NoReGeo focuses on evaluating whether LLMs can inherently encode spatial relationships and recognize geometric properties directly. Our benchmark comprises 2,500 trivial geometric problems spanning 25 categories, each carefully crafted to be solvable purely through native geometric understanding, assuming known object locations. We assess a range of state-of-the-art models on NoReGeo, including frontier models like GPT-4, observing that even the most advanced systems achieve an overall maximum of 65% accuracy in binary classification tasks. Further, our ablation experiments demonstrate that such geometric understanding does not emerge through fine-tuning alone, indicating that effective training for geometric comprehension requires a specialized approach from the outset. Our findings highlight a significant gap in current LLMs' ability to natively grasp geometric concepts, providing a foundation for future research toward models with true geometric cognition.

Diffusion policies excel at robotic manipulation by naturally modeling multimodal action distributions in high-dimensional spaces. Nevertheless, diffusion policies suffer from diffusion representation collapse: semantically similar observations are mapped to indistinguishable features, ultimately impairing their ability to handle subtle but critical variations required for complex robotic manipulation. To address this problem, we propose D²PPO (Diffusion Policy Policy Optimization with Dispersive Loss). D²PPO introduces dispersive loss regularization that combats representation collapse by treating all hidden representations within each batch as negative pairs. D²PPO compels the network to learn discriminative representations of similar observations, thereby enabling the policy to identify subtle yet crucial differences necessary for precise manipulation. In evaluation, we find that early-layer regularization benefits simple tasks, while late-layer regularization sharply enhances performance on complex manipulation tasks. On RoboMimic benchmarks, D²PPO achieves an average improvement of 22.7% in pre-training and 26.1% after fine-tuning, setting new SOTA results. In comparison with SOTA, the results of real-world experiments on a Franka Emika Panda robot show the excitingly high success rate of our method. The superiority of our method is especially evident in complex tasks.

Unified video and action prediction models hold great potential for robotic manipulation, as future observations offer contextual cues for planning, while actions reveal how interactions shape the environment. However, most existing approaches treat observation and action generation in a monolithic and goal-agnostic manner, often leading to semantically misaligned predictions and incoherent behaviors. To this end, we propose H-GAR, a Hierarchical interaction framework via Goal-driven observation-Action Refinement. To anchor prediction to the task objective, H-GAR first produces a goal observation and a coarse action sketch that outline a high-level route toward the goal. To enable explicit interaction between observation and action under the guidance of the goal observation for more coherent decision-making, we devise two synergistic modules. (1) Goal-Conditioned Observation Synthesizer (GOS) synthesizes intermediate observations based on the coarse-grained actions and the predicted goal observation. (2) Interaction-Aware Action Refiner (IAAR) refines coarse actions into fine-grained, goal-consistent actions by leveraging feedback from the intermediate observations and a Historical Action Memory Bank that encodes prior actions to ensure temporal consistency. By integrating goal grounding with explicit action-observation interaction in a coarse-to-fine manner, H-GAR enables more accurate manipulation. Extensive experiments on both simulation and real-world robotic manipulation tasks demonstrate that H-GAR achieves state-of-the-art performance.

Enabling robots to grasp disorganized cloth for efficient storage is valuable in robot-assisted room organization. Diverse deformations of cloth and the stacking of multiple items limit grasping-pose estimation that relies on annotations. This necessitates segmenting each cloth item in an unsupervised manner before estimating the grasping position. However, existing segmentation methods primarily focus on improving metrics such as Intersection-over-Union and Pixel Accuracy, which cannot effectively measure the segmentation errors of the cloth area and thus lead to failure grasping position estimation. To address this challenge, we use False Discovery Rate (FDR) as a novel measure of segmentation errors and analyze its impact on grasping success. Our preliminary study reveals a negative correlation between segmentation FDR and grasping success rate, highlighting the need for more reliable segmentation in cluttered cloth scenarios. Therefore, we propose an unsupervised cloth segmentation network based on feature distance-weighted constraints, designed to reduce the false discovery rate in cloth area perception without requiring expensive pixel-level manual annotations. Additionally, to estimate the grasping position on the perceived cloth area, we introduce a strategy based on cloth surface wrinkle analysis, which operates without the need for annotations or training. By integrating the proposed segmentation network and grasping strategy, we develop a robotic system capable of sequentially grasping cluttered cloth from a table. Extensive real-world robotic experiments demonstrate the effectiveness of our approach, outperforming multiple baseline methods in segmentation FDR and grasping success rate.

Tactile sensing offers rich and complementary information to vision and language, enabling robots to perceive fine-grained object properties. However, existing tactile sensors lack standardization, leading to redundant features that hinder cross-sensor generalization. Moreover, existing methods fail to fully integrate the intermediate communication among tactile, language, and vision modalities. To address this, we propose TLV-CoRe, a CLIP-based Tactile-Language-Vision Collaborative Representation learning method. TLV-CoRe introduces a Sensor-Aware Modulator to unify tactile features across different sensors and employs tactile-irrelevant decoupled learning to disentangle irrelevant tactile features. Additionally, a Unified Bridging Adapter is introduced to enhance tri-modal interaction within the shared representation space. To fairly evaluate the effectiveness of tactile models, we further propose the RSS evaluation framework, focusing on Robustness, Synergy, and Stability across different methods. Experimental results demonstrate that TLV-CoRe significantly improves sensor-agnostic representation learning and cross-modal alignment, offering a new direction for multimodal tactile representation.

Autonomous execution of long-horizon, contact-rich manipulation tasks traditionally requires extensive real-world data and expert engineering, posing significant cost and scalability challenges. This paper proposes a novel framework integrating hierarchical semantic decomposition, reinforcement learning (RL), visual language models (VLMs), and knowledge distillation to overcome these limitations. Complex tasks are decomposed into atomic skills, with RL-trained policies for each primitive exclusively in simulation. Crucially, our RL formulation incorporates explicit force constraints to prevent object damage during delicate interactions. VLMs perform high-level task decomposition and skill planning, generating diverse expert demonstrations. These are distilled into a unified policy via Visual-Tactile Diffusion Policy for end-to-end execution. We conduct comprehensive ablation studies exploring different VLM-based task planners to identify optimal demonstration generation pipelines, and systematically compare imitation learning algorithms for skill distillation. Extensive simulation experiments and physical deployment validate that our approach achieves policy learning for long-horizon manipulation without costly human demonstrations, while the VLM-guided atomic skill framework enables scalable generalization to diverse tasks.

Vision-and-Language Navigation (VLN) requires an agent to dynamically explore complex 3D environments following human instructions. Recent research underscores the potential of harnessing large language models (LLMs) for VLN, given their commonsense knowledge and general reasoning capabilities. Despite their strengths, a substantial gap in task completion performance persists between LLM-based approaches and domain experts, as LLMs inherently struggle to comprehend real-world spatial correlations precisely; additionally, LLM inference can make the decision-making process considerably inefficient. To address these issues, we propose a novel dual-process thinking framework dubbed R3, integrating LLMs' generalization capabilities with VLN-specific expertise in a zero-shot manner. The framework comprises three core modules: Runner, Ruminator, and Regulator. The Runner is a lightweight transformer-based expert model that ensures efficient and accurate navigation under regular circumstances. The Ruminator employs a multimodal LLM as the backbone and adopts chain-of-thought (CoT) prompting to elicit structured reasoning from the LLM. The Regulator monitors the navigation progress and controls the appropriate thinking mode according to three criteria, integrating Runner and Ruminator harmoniously. Experimental results illustrate that R3 significantly outperforms other state-of-the-art methods, exceeding 3.28% and 3.30% in SPL and RGSPL respectively on the REVERIE benchmark, highlighting the effectiveness of our method in handling challenging VLN tasks.

Dexterous grasping remains a fundamental yet challenging problem in robotics. A general-purpose robot must be capable of grasping diverse objects in arbitrary scenarios. However, existing research typically relies on restrictive assumptions, such as single-object settings or limited environments, showing constrained generalization. We present DexGraspVLA, a hierarchical framework for robust generalization in language-guided general dexterous grasping and beyond. It utilizes a pre-trained Vision-Language model as the high-level planner and learns a diffusion-based low-level Action controller. The key insight to achieve generalization lies in iteratively transforming diverse language and visual inputs into domain-invariant representations via foundation models, where imitation learning can be effectively applied due to the alleviation of domain shift. Notably, our method achieves a 90+% dexterous grasping success rate under thousands of challenging unseen cluttered scenes. Empirical analysis confirms the consistency of internal model behavior across environmental variations, validating our design. DexGraspVLA also, for the first time, simultaneously demonstrates free-form long-horizon prompt execution, robustness to adversarial objects and human disturbance, and failure recovery. Extended application to nonprehensile grasping further proves its generality.